Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 10992
    Prev
    Next
    INDEX
    Explanations

    actions involving violence or crime

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    46
    +0.12
    0.6%
    277
    +0.11
    0.5%
    28
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.12
    0.06
    46
    +0.11
    0.05
    748
    +0.10
    0.04
    Negative Logits
    peak
    -0.77
    season
    -0.72
    DragonMagazine
    -0.68
    lux
    -0.67
    Unity
    -0.67
    hist
    -0.66
    pure
    -0.66
    ancel
    -0.66
    ance
    -0.65
    microsoft
    -0.65
    POSITIVE LOGITS
     subsequently
    1.17
     then
    1.04
     underwent
    0.99
     transported
    0.97
     reportedly
    0.95
     lodged
    0.95
     proceeded
    0.94
     injuring
    0.94
     drove
    0.93
     detonated
    0.93
    Activations Density 0.218%

    No Known Activations